用结构化方法+大模型，让解数学应用题更清晰
SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation
- 基于问题结构分类型，引导分步推理
- 在GSM8K上优于GPT-3.5 Turbo，推理更清晰
- 适合需要提升解题逻辑的学生和教育AI研究者
许多学生在解决数学应用题（MWPs）时难以识别关键信息并选择合适的数学运算。基于证据的结构化教学（SBI）通过按问题结构分类来提升解题准确率。本文提出一种结合大语言模型（LLM）的结构化教学检索增强生成框架（SBI-RAG），强调分步推理，利用结构模板引导解题生成。在GSM8K数据集上评估，相比GPT-4和GPT-3.5 Turbo，SBI-RAG在推理清晰度上表现更优，并引入“推理得分”衡量解题质量。结果表明，该方法能有效提升推理过程的结构性与可解释性，潜在有助于学生学习。
原文摘要 · Abstract (English)
Many students struggle with math word problems (MWPs), often finding it difficult to identify key information and select the appropriate mathematical operations. Schema-based instruction (SBI) is an evidence-based strategy that helps students categorize problems based on their structure, improving problem-solving accuracy. Building on this, we propose a Schema-Based Instruction Retrieval-Augmented Generation (SBI-RAG) framework that incorporates a large language model (LLM). Our approach emphasizes step-by-step reasoning by leveraging schemas to guide solution generation. We evaluate its performance on the GSM8K dataset, comparing it with GPT-4 and GPT-3.5 Turbo, and introduce a "reasoning score" metric to assess solution quality. Our findings suggest that SBI-RAG enhances reasoning clarity and facilitates a more structured problem-solving process potentially providing educational benefits for students.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。